mcp-perplexity-search
by spences10
An MCP server integrating Perplexity's AI API with LLMs. It provides advanced chat completion capabilities with specialized prompt templates for various use cases.
Last updated: N/A
What is mcp-perplexity-search?
An MCP server that integrates Perplexity's AI API to provide advanced chat completion capabilities for LLMs. It utilizes specialized prompt templates to address various use cases.
How to use mcp-perplexity-search?
Configure the server through your MCP client by adding the appropriate configuration snippet to your Cline MCP settings or Claude Desktop configuration. Ensure you set the PERPLEXITY_API_KEY environment variable with your Perplexity API key. Then, use the chat_completion API with the specified parameters to generate chat completions.
Key features of mcp-perplexity-search
Advanced chat completion using Perplexity's AI models
Predefined prompt templates for common scenarios
Custom template support for specialized use cases
Multiple output formats (text, markdown, JSON)
Optional source URL inclusion in responses
Configurable model parameters (temperature, max tokens)
Support for various Perplexity models including Sonar and LLaMA
Use cases of mcp-perplexity-search
Technical documentation generation
Security best practices analysis
Code review and improvements
API documentation in structured format
FAQ from mcp-perplexity-search
What is the PERPLEXITY_API_KEY?
What is the PERPLEXITY_API_KEY?
Your personal API key from Perplexity, required to authenticate with their service.
What is the default model used by the server?
What is the default model used by the server?
The default model is 'sonar'.
Can I use custom prompt templates?
Can I use custom prompt templates?
Yes, you can define custom prompt templates with a system message, format preference, and whether to include sources.
What output formats are supported?
What output formats are supported?
The server supports 'text', 'markdown', and 'json' output formats.
Is this project still maintained?
Is this project still maintained?
No, this repository is no longer maintained. The functionality is now available in mcp-omnisearch.